Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3129 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1513626 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1440017 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1441724 (Python Code)

Max Activating Token Index: 33

Text #3

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1500328 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1583917 (Python Code)

Max Activating Token Index: 176

Text #5

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1597860 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1612924 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0634. Min Act: -0.0001

Data Index: 1484002 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1427903 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1546175 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1380350 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1631133 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1575693 (Python Code)

Max Activating Token Index: 1007

Text #13

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1511306 (Python Code)

Max Activating Token Index: 246

Text #14

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1543975 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0592. Min Act: -0.0001

Data Index: 1476262 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1529488 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1560066 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1654201 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 0.0814. Min Range: -0.0814

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1571649 (Python Code)

Max Activating Token Index: 65